Matching Items (5)
Filtering by

Clear all filters

132967-Thumbnail Image.png

Learning Generalized Heuristics Using Deep Neural Networks

Description
Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that,…

Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
ContributorsNakhleh, Julia Blair (Author) / Srivastava, Siddharth (Thesis director) / Fainekos, Georgios (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
135047-Thumbnail Image.png

Conjugating Honorifics in English-to-Japanese Machine Translation

Description
This research lays down foundational work in the semantic reconstruction of linguistic politeness in English-to-Japanese machine translation and thereby advances semantic-based automated translation of English into other natural languages. I developed a Java project called the PoliteParser that is intended as a plug-in to existing semantic parsers to determine whether…

This research lays down foundational work in the semantic reconstruction of linguistic politeness in English-to-Japanese machine translation and thereby advances semantic-based automated translation of English into other natural languages. I developed a Java project called the PoliteParser that is intended as a plug-in to existing semantic parsers to determine whether verbs in dialogue in an English corpus should be conjugated into the plain or the polite honorific form when translated into Japanese. The PoliteParser bases this decision off of semantic information about the social relationships between the speaker and the listener, the speaker's personality, and the circumstances of the utterance. Testing undergone during the course of this research demonstrates that the PoliteParser can achieve levels of accuracy 31 percentage points higher than that of statistical translation systems when integrated with a semantic parser and 54 percentage points higher when used with pre-parsed data.
ContributorsGuiou, Jared Tyler (Author) / Baral, Chitta (Thesis director) / Tanno, Koji (Committee member) / School of International Letters and Cultures (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
134100-Thumbnail Image.png

Virtual Reality Drum Training System

Description
Can a skill taught in a virtual environment be utilized in the physical world? This idea is explored by creating a Virtual Reality game for the HTC Vive to teach users how to play the drums. The game focuses on developing the user's muscle memory, improving the user's ability to…

Can a skill taught in a virtual environment be utilized in the physical world? This idea is explored by creating a Virtual Reality game for the HTC Vive to teach users how to play the drums. The game focuses on developing the user's muscle memory, improving the user's ability to play music as they hear it in their head, and refining the user's sense of rhythm. Several different features were included to achieve this such as a score, different levels, a demo feature, and a metronome. The game was tested for its ability to teach and for its overall enjoyability by using a small sample group. Most participants of the sample group noted that they felt as if their sense of rhythm and drumming skill level would improve by playing the game. Through the findings of this project, it can be concluded that while it should not be considered as a complete replacement for traditional instruction, a virtual environment can be successfully used as a learning aid and practicing tool.
ContributorsDinapoli, Allison (Co-author) / Tuznik, Richard (Co-author) / Kobayashi, Yoshihiro (Thesis director) / Nelson, Brian (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Computing and Informatics Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
192577-Thumbnail Image.png

American Sign Language Fingerspelling and Gestures in Computer Science Curriculum

Description

American Sign Language (ASL) is used for Deaf and Hard of Hearing (DHH) individuals to communicate and learn in a classroom setting. In ASL, fingerspelling and gestures are two primary components used for communication. Fingerspelling is commonly used for words that do not have a specifically designated sign or gesture.…

American Sign Language (ASL) is used for Deaf and Hard of Hearing (DHH) individuals to communicate and learn in a classroom setting. In ASL, fingerspelling and gestures are two primary components used for communication. Fingerspelling is commonly used for words that do not have a specifically designated sign or gesture. In technical contexts, such as Computer Science curriculum, there are many technical terms that fall under this category. Most of its jargon does not have standardized ASL gestures; therefore, students, educators, and interpreters alike have been reliant on fingerspelling, which poses challenges for all parties. This study investigates the efficacy of both fingerspelling and gestures with fifteen technical terms that do have standardized gestures. The terms’ fingerspelling and gesture are assessed based on preference, ease of use, ease of learning, and time by research subjects who were selected as DHH individuals familiar with ASL.

The data is collected in a series of video recordings by research subjects as well as a post-participation questionnaire. Each research subject has produced thirty total videos, two videos to fingerspell and gesture each technical term. Afterwards, they completed a post-participation questionnaire in which they indicated their preference and how easy it was to learn and use both fingerspelling and gestures. Additionally, the videos have been analyzed to determine the time difference between fingerspelling and gestures. Analysis reveals that gestures are favored over fingerspelling as they are generally preferred, considered easier to learn and use, and faster. These results underscore the significance for standardized gestures in the Computer Science curriculum for accessible learning that enhances communication and promotes inclusion.
ContributorsKarim, Bushra (Author) / Gupta, Sandeep (Thesis director) / Hossain, Sameena (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor)
Created2024-05

Building a Machine Learning Model to Predict Spring Wheat Crop Yield in Yuma, Arizona

Description
Machine learning(ML) has been on the rise in many fields including agriculture. It is used for many things including crop yield prediction which is meant to help farmers decide when and what to grow based on the model. Many models have been built for various crops and areas of the…

Machine learning(ML) has been on the rise in many fields including agriculture. It is used for many things including crop yield prediction which is meant to help farmers decide when and what to grow based on the model. Many models have been built for various crops and areas of the world utilizing various sources of data. However, there is yet to exist a model designed to predict any crop’s yield in Yuma Arizona, one of the premier places to grow crops in America. For this, I built a dataset from farm documentation that describes the actions taken before, during, and after a crop is being grown. To supplement this data, ecological data was also used so data such as temperature, heat units, soil type, and soil water holding capacity were included. I used this dataset to train various regression models where I discovered that the farm data was useful, but only when used in conjunction with the ecological data.
ContributorsJohnson, Nicholas (Author) / Kerner, Hannah (Thesis director) / Bandaru, Varaprasad (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05